© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 15293
    Prev
    Next
    INDEX
    Explanations

    changed, began, help, add

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ensuing
    -0.09
    Outlined
    -0.08
    uzzi
    -0.08
    jec
    -0.08
     iov
    -0.08
     terse
    -0.08
    EA
    -0.08
    wdx
    -0.08
     (--
    -0.08
     Willis
    -0.08
    POSITIVE LOGITS
     surprises
    0.21
     something
    0.19
     interesting
    0.19
     differently
    0.18
     surprising
    0.17
     complic
    0.16
     Interesting
    0.16
    something
    0.15
     consequences
    0.15
    Interesting
    0.15
    Activations Density 0.635%

    No Known Activations